Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Chinese sentence semantic intelligent matching method and device based on multi-granularity fusion model

A technology that integrates models and matching methods. It is applied in semantic analysis, neural learning methods, biological neural network models, etc. It can solve the problems of inaccurate sentence matching and incomplete semantic analysis of single-granularity models, so as to improve accuracy and alleviate categories. Imbalance problem, the effect of improving representation

Active Publication Date: 2021-06-08
QILU UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical task of the present invention is to provide a Chinese sentence semantic intelligent matching method and device based on a multi-granularity fusion model to solve the problems of incomplete semantic analysis and inaccurate sentence matching of a single-granularity model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Chinese sentence semantic intelligent matching method and device based on multi-granularity fusion model
  • Chinese sentence semantic intelligent matching method and device based on multi-granularity fusion model
  • Chinese sentence semantic intelligent matching method and device based on multi-granularity fusion model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0142] as attached figure 1 Shown, the Chinese sentence semantic intelligent matching method based on multi-granularity fusion model of the present invention, the method is specifically as follows:

[0143] S1, build text matching knowledge base; figure 2 As shown, the details are as follows:

[0144] S101. Use a crawler to obtain original data: crawl the question set on the Internet public question-and-answer platform to obtain the original similar sentence knowledge base; or use the sentence matching data set published on the Internet as the original similar sentence knowledge base;

[0145] There are a large amount of question-and-answer data and recommendations for similar questions in public question-and-answer platforms on the Internet, which are open to the public. Therefore, according to the characteristics of the question answering platform, a corresponding crawler program can be designed to obtain a collection of text sentences with similar semantics, so as to bui...

Embodiment 2

[0270] as attached Figure 10 Shown, the Chinese sentence semantic intelligent matching device based on multi-granularity fusion model of the present invention, this device comprises,

[0271] The text matching knowledge base construction unit is used to use the crawler program to crawl the question set on the Internet public question and answer platform, or use the text matching data set published on the Internet as the original similar sentence knowledge base, and then preprocess the original similar sentence knowledge base , the main operation is to perform hyphenation processing and word segmentation processing on each sentence in the original similar sentence knowledge base, thereby constructing a text matching knowledge base for model training; the text matching knowledge base construction unit includes,

[0272] Crawl the original data sub-unit, which is used to crawl the question set on the Internet public question-and-answer platform, or use the text matching data set...

Embodiment 3

[0290] Based on the storage medium of Embodiment 1, there are a plurality of instructions stored therein, and the instructions are loaded by the processor to execute the steps of the Chinese sentence semantic intelligent matching method based on the multi-granularity fusion model of Embodiment 1.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a Chinese sentence semantic intelligent matching method and device based on a multi-granularity fusion model, which belongs to the field of artificial intelligence and natural language processing. Accurate, the technical solution adopted is: the method is specifically as follows: S1, constructing a text matching knowledge base; S2, constructing a training data set for a text matching model; S3, constructing a multi-granularity fusion model; specifically as follows: S301, constructing a character word mapping transformation Table; S302, building an input layer; S303, building a multi-granularity embedding layer; S304, building a multi-granularity fusion coding layer; S305, building an interactive matching layer; S306, building a prediction layer; S4, training a multi-granularity fusion model. The device includes a text matching knowledge base construction unit, a text matching model training data set construction unit, a multi-granularity fusion model construction unit and a multi-granularity fusion model training unit.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and natural language processing, in particular to a Chinese sentence semantic intelligent matching method and device based on a multi-granularity fusion model. Background technique [0002] Sentence semantic matching plays a key role in many natural language processing tasks, such as question answering (QA), natural language inference (NLI), machine translation (MT), etc. The key to sentence semantic matching is to calculate the matching degree between the semantics of a given sentence pair. Sentences can be segmented at different granularities, such as characters, words, and phrases. Currently, the commonly used text segmentation granularity is words, especially in the Chinese field. [0003] At present, most Chinese sentence semantic matching models are oriented to word granularity, while ignoring other segmentation granularities. These models cannot fully capture the semantic features...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/211G06F40/289G06F40/30G06F16/33G06F16/35G06N3/04G06N3/08G06K9/62
CPCG06F16/3344G06F16/35G06N3/08G06N3/048G06N3/045G06F18/241
Inventor 鹿文鹏王荣耀张旭贾瑞祥郭韦钰张维玉
Owner QILU UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com